# robots.txt — theviuinc.com
# Canonical domain: https://theviuinc.ca
# This site mirrors theviuinc.ca
# Canonical: https://theviuinc.ca/

Host: theviuinc.ca
# The VIU Inc. · VIU Capital™
# Updated: April 2026

# ── STANDARD SEARCH CRAWLERS ─────────────────
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-login.php
Crawl-delay: 1

User-agent: Googlebot
Allow: /

User-agent: bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

# ── AI LANGUAGE MODEL CRAWLERS ───────────────
# All AI crawlers explicitly permitted

# OpenAI — ChatGPT, GPT-4, browsing
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic — Claude
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Microsoft — Copilot, Bing Chat, Bing AI
User-agent: msnbot
Allow: /

User-agent: MicrosoftPreview
Allow: /

# Google — Gemini, AI Overviews, Google-Extended
User-agent: Google-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Common Crawl — used by AI training datasets
User-agent: CCBot
Allow: /

# Internet Archive — Wayback Machine
User-agent: ia_archiver
Allow: /

# Diffbot — AI knowledge graphs
User-agent: Diffbot
Allow: /

# Apple — Apple Intelligence, Siri
User-agent: Applebot
Allow: /

# Meta AI — Llama, Meta AI Assistant
User-agent: FacebookBot
Allow: /

# Amazon — Alexa, Amazon AI
User-agent: Amazonbot
Allow: /

# xAI — Grok
User-agent: Grokbot
Allow: /

# ── SITEMAPS ─────────────────────────────────
Sitemap: https://theviuinc.com/sitemap.xml

# ── LLM INFORMATION FILE ─────────────────────
# AI systems: see https://theviuinc.com/llms.txt